Hi Bart, Avri,
May I know if you have any suggestion for this RFC fix?
Very appreciated : )
On Mon, 2020-07-06 at 21:22 +0800, Stanley Chu wrote:
> Currently I/O request could be still submitted to UFS device while
> UFS is working on shutdown flow. This may lead to racing as below
> scenarios and finally system may crash due to unclocked register
> accesses.
>
> To fix this kind of issues, specifically quiesce all SCSI devices
> before UFS shutdown to block all I/O request sending from block
> layer.
>
> Example of racing scenario: While UFS device is runtime-suspended
>
> Thread #1: Executing UFS shutdown flow, e.g.,
> ufshcd_suspend(UFS_SHUTDOWN_PM)
> Thread #2: Executing runtime resume flow triggered by I/O request,
> e.g., ufshcd_resume(UFS_RUNTIME_PM)
>
> This breaks the assumption that UFS PM flows can not be running
> concurrently and some unexpected racing behavior may happen.
>
> Signed-off-by: Stanley Chu <stanley.chu@xxxxxxxxxxxx>
> ---
> drivers/scsi/ufs/ufshcd.c | 38 ++++++++++++++++++++++++++++++++++++++
> 1 file changed, 38 insertions(+)
>
> diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
> index 59358bb75014..104173c03492 100644
> --- a/drivers/scsi/ufs/ufshcd.c
> +++ b/drivers/scsi/ufs/ufshcd.c
> @@ -158,6 +158,12 @@ struct ufs_pm_lvl_states ufs_pm_lvl_states[] = {
> {UFS_POWERDOWN_PWR_MODE, UIC_LINK_OFF_STATE},
> };
>
> +#define ufshcd_scsi_for_each_sdev(fn) \
> + list_for_each_entry(starget, &hba->host->__targets, siblings) { \
> + __starget_for_each_device(starget, NULL, \
> + fn); \
> + }
> +
> static inline enum ufs_dev_pwr_mode
> ufs_get_pm_lvl_to_dev_pwr_mode(enum ufs_pm_level lvl)
> {
> @@ -8588,6 +8594,19 @@ int ufshcd_runtime_idle(struct ufs_hba *hba)
> }
> EXPORT_SYMBOL(ufshcd_runtime_idle);
>
> +static void ufshcd_cleanup_queue(struct scsi_device *sdev, void *data)
> +{
> + if (sdev->request_queue)
> + blk_cleanup_queue(sdev->request_queue);
> +}
> +
> +static void ufshcd_quiece_sdev(struct scsi_device *sdev, void *data)
> +{
> + /* Suspended devices are already quiecsed and shall be skipped */
> + if (!pm_runtime_suspended(&sdev->sdev_gendev))
> + scsi_device_quiesce(sdev);
> +}
> +
> /**
> * ufshcd_shutdown - shutdown routine
> * @hba: per adapter instance
> @@ -8599,6 +8618,7 @@ EXPORT_SYMBOL(ufshcd_runtime_idle);
> int ufshcd_shutdown(struct ufs_hba *hba)
> {
> int ret = 0;
> + struct scsi_target *starget;
>
> if (!hba->is_powered)
> goto out;
> @@ -8612,7 +8632,25 @@ int ufshcd_shutdown(struct ufs_hba *hba)
> goto out;
> }
>
> + /*
> + * Quiesce all SCSI devices to prevent any non-PM requests sending
> + * from block layer during and after shutdown.
> + *
> + * Here we can not use blk_cleanup_queue() since PM requests
> + * (with BLK_MQ_REQ_PREEMPT flag) are still required to be sent
> + * through block layer. Therefore SCSI command queued after the
> + * scsi_target_quiesce() call returned will block until
> + * blk_cleanup_queue() is called.
> + *
> + * Besides, scsi_target_"un"quiesce (e.g., scsi_target_resume) can
> + * be ignored since shutdown is one-way flow.
> + */
> + ufshcd_scsi_for_each_sdev(ufshcd_quiece_sdev);
> +
> ret = ufshcd_suspend(hba, UFS_SHUTDOWN_PM);
> +
> + /* Set queue as dying to not block queueing commands */
> + ufshcd_scsi_for_each_sdev(ufshcd_cleanup_queue);
> out:
> if (ret)
> dev_err(hba->dev, "%s failed, err %d\n", __func__, ret);
